{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:13:37Z","timestamp":1742933617540,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031270765"},{"type":"electronic","value":"9783031270772"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-27077-2_30","type":"book-chapter","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:03:10Z","timestamp":1679979790000},"page":"385-396","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["COMIM-GAN: Improved Text-to-Image Generation via\u00a0Condition Optimization and Mutual Information Maximization"],"prefix":"10.1007","author":[{"given":"Longlong","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,29]]},"reference":[{"issue":"8","key":"30_CR1","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Patt. Anal. Mach. Intell. 35(8), 1798\u20131828 (2013)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"30_CR2","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"30_CR3","first-page":"1","volume":"70","author":"C Cheng","year":"2021","unstructured":"Cheng, C., Wu, X.J., Xu, T., Chen, G.: Unifusion: a lightweight unified image fusion network. IEEE Trans. Instrument. Measure. 70, 1\u201314 (2021)","journal-title":"IEEE Trans. Instrument. Measure."},{"key":"30_CR4","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"30_CR5","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"30_CR6","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Lee, K.S., Tran, N.T., Cheung, N.M.: Infomax-gan: Improved adversarial image generation via information maximization and contrastive learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3942\u20133952 (2021)","DOI":"10.1109\/WACV48630.2021.00399"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Liao, W., Hu, K., Yang, M.Y., Rosenhahn, B.: Text to image generation with semantic-spatial aware gan. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18187\u201318196 (2022)","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"30_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"30_CR10","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(11), 2579\u20132605 (2008)"},{"key":"30_CR11","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. Computer Science. pp. 2672\u20132680 (2014)"},{"key":"30_CR12","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning, pp. 1060\u20131069. PMLR (2016)"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Ruan, S., et al.: Dae-gan: Dynamic aspect-aware gan for text-to-image synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13960\u201313969 (2021)","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"30_CR14","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. In: Advances in Neural Information Processing Systems, vol. 29, pp. 2234\u20132242 (2016)"},{"issue":"5","key":"30_CR15","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.1109\/TCSVT.2021.3103677","volume":"32","author":"Z Shen","year":"2021","unstructured":"Shen, Z., Wu, X.J., Xu, T.: Fexnet: foreground extraction network for human action recognition. IEEE Trans. Circ. Syst. Video Technol. 32(5), 3141\u20133151 (2021)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Souza, D.M., Wehrmann, J., Ruiz, D.D.: Efficient neural architecture for text-to-image synthesis. In: 2020 International Joint Conference on Neural Networks (IJCNN)., pp. 1\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9207584"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Tan, H., Liu, X., Li, X., Zhang, Y., Yin, B.: Semantics-enhanced adversarial nets for text-to-image synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10501\u201310510 (2019)","DOI":"10.1109\/ICCV.2019.01060"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Tao, M., Tang, H., Wu, F., Jing, X.Y., Bao, B.K., Xu, C.: Df-gan: A simple and effective baseline for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16515\u201316525 (2022)","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"30_CR20","unstructured":"Tschannen, M., Djolonga, J., Rubenstein, P.K., Gelly, S., Lucic, M.: On mutual information maximization for representation learning. arXiv preprint arXiv:1907.13625 (2019)"},{"key":"30_CR21","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"issue":"11","key":"30_CR23","doi-asserted-by":"publisher","first-page":"5596","DOI":"10.1109\/TIP.2019.2919201","volume":"28","author":"T Xu","year":"2019","unstructured":"Xu, T., Feng, Z.H., Wu, X.J., Kittler, J.: Learning adaptive discriminative correlation filters via temporal consistency preserving spatial feature selection for robust visual object tracking. IEEE Trans. Image Process. 28(11), 5596\u20135609 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"30_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107172","volume":"102","author":"T Xu","year":"2020","unstructured":"Xu, T., Feng, Z.H., Wu, X.J., Kittler, J.: An accelerated correlation filter tracker. Pattern Recogn. 102, 107172 (2020)","journal-title":"Pattern Recogn."},{"issue":"5","key":"30_CR25","doi-asserted-by":"publisher","first-page":"1359","DOI":"10.1007\/s11263-021-01435-1","volume":"129","author":"T Xu","year":"2021","unstructured":"Xu, T., Feng, Z., Wu, X.J., Kittler, J.: Adaptive channel selection for robust visual object tracking with discriminative correlation filters. Int. J. Comput. Vision 129(5), 1359\u20131375 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Xu, T., Wu, X.J., Kittler, J.: Non-negative subspace representation learning scheme for correlation filter based tracking. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 1888\u20131893. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8546146"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., Metaxas, D.N.: Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5907\u20135915 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Schomaker, L.: Dtgan: Dual attention generative adversarial networks for text-to-image generation. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2021)","DOI":"10.1109\/IJCNN52387.2021.9533527"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., Yang, Y.: Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5802\u20135810 (2019)","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27077-2_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:14:58Z","timestamp":1679980498000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27077-2_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031270765","9783031270772"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27077-2_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"86","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}